/**

 * Copyright (c) 2000-2001 Aaron D. Gifford

 * Copyright (c) 2013-2014 Pavol Rusnak

 * All rights reserved.

 *

 * Redistribution and use in source and binary forms, with or without

 * modification, are permitted provided that the following conditions

 * are met:

 * 1. Redistributions of source code must retain the above copyright

 *    notice, this list of conditions and the following disclaimer.

 * 2. Redistributions in binary form must reproduce the above copyright

 *    notice, this list of conditions and the following disclaimer in the

 *    documentation and/or other materials provided with the distribution.

 * 3. Neither the name of the copyright holder nor the names of contributors

 *    may be used to endorse or promote products derived from this software

 *    without specific prior written permission.

 *

 * THIS SOFTWARE IS PROVIDED BY THE AUTHOR AND CONTRIBUTOR(S) ``AS IS'' AND

 * ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE

 * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE

 * ARE DISCLAIMED.  IN NO EVENT SHALL THE AUTHOR OR CONTRIBUTOR(S) BE LIABLE

 * FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL

 * DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS

 * OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION)

 * HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT

 * LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY

 * OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF

 * SUCH DAMAGE.

 */

#include <string.h>

#include <stdint.h>

#include "sha2.h"

#include "memzero.h"

#include "byte_order.h"

/*

 * ASSERT NOTE:

 * Some sanity checking code is included using assert().  On my FreeBSD

 * system, this additional code can be removed by compiling with NDEBUG

 * defined.  Check your own systems manpage on assert() to see how to

 * compile WITHOUT the sanity checking code on your system.

 *

 * UNROLLED TRANSFORM LOOP NOTE:

 * You can define SHA2_UNROLL_TRANSFORM to use the unrolled transform

 * loop version for the hash transform rounds (defined using macros

 * later in this file).  Either define on the command line, for example:

 *

 *   cc -DSHA2_UNROLL_TRANSFORM -o sha2 sha2.c sha2prog.c

 *

 * or define below:

 *

 *   #define SHA2_UNROLL_TRANSFORM

 *

 */

/*** SHA-256/384/512 Machine Architecture Definitions *****************/

/*

 * BYTE_ORDER NOTE:

 *

 * Please make sure that your system defines BYTE_ORDER.  If your

 * architecture is little-endian, make sure it also defines

 * LITTLE_ENDIAN and that the two (BYTE_ORDER and LITTLE_ENDIAN) are

 * equivilent.

 *

 * If your system does not define the above, then you can do so by

 * hand like this:

 *

 *   #define LITTLE_ENDIAN 1234

 *   #define BIG_ENDIAN    4321

 *

 * And for little-endian machines, add:

 *

 *   #define BYTE_ORDER LITTLE_ENDIAN

 *

 * Or for big-endian machines:

 *

 *   #define BYTE_ORDER BIG_ENDIAN

 *

 * The FreeBSD machine this was written on defines BYTE_ORDER

 * appropriately by including <sys/types.h> (which in turn includes

 * <machine/endian.h> where the appropriate definitions are actually

 * made).

 */

#if !defined(BYTE_ORDER) || (BYTE_ORDER != LITTLE_ENDIAN && BYTE_ORDER != BIG_ENDIAN)

#error Define BYTE_ORDER to be equal to either LITTLE_ENDIAN or BIG_ENDIAN

#endif

typedef uint8_t  sha2_byte; /* Exactly 1 byte */

typedef uint32_t sha2_word32; /* Exactly 4 bytes */

typedef uint64_t sha2_word64; /* Exactly 8 bytes */

/*** SHA-256/384/512 Various Length Definitions ***********************/

/* NOTE: Most of these are in sha2.h */

#define   SHA1_SHORT_BLOCK_LENGTH (SHA1_BLOCK_LENGTH - 8)

#define SHA256_SHORT_BLOCK_LENGTH (SHA256_BLOCK_LENGTH - 8)

#define SHA512_SHORT_BLOCK_LENGTH (SHA512_BLOCK_LENGTH - 16)

/*

 * Macro for incrementally adding the unsigned 64-bit integer n to the

 * unsigned 128-bit integer (represented using a two-element array of

 * 64-bit words):

 */

#define ADDINC128(w,n)  { \

  (w)[0] += (sha2_word64)(n); \

  if ((w)[0] < (n)) { \

    (w)[1]++; \

  } \

}

#define MEMCPY_BCOPY(d,s,l) memcpy((d), (s), (l))

/*** THE SIX LOGICAL FUNCTIONS ****************************************/

/*

 * Bit shifting and rotation (used by the six SHA-XYZ logical functions:

 *

 *   NOTE:  In the original SHA-256/384/512 document, the shift-right

 *   function was named R and the rotate-right function was called S.

 *   (See: http://csrc.nist.gov/cryptval/shs/sha256-384-512.pdf on the

 *   web.)

 *

 *   The newer NIST FIPS 180-2 document uses a much clearer naming

 *   scheme, SHR for shift-right, ROTR for rotate-right, and ROTL for

 *   rotate-left.  (See:

 *   http://csrc.nist.gov/publications/fips/fips180-2/fips180-2.pdf

 *   on the web.)

 *

 *   WARNING: These macros must be used cautiously, since they reference

 *   supplied parameters sometimes more than once, and thus could have

 *   unexpected side-effects if used without taking this into account.

 */

/* Shift-right (used in SHA-256, SHA-384, and SHA-512): */

#define SHR(b,x)    ((x) >> (b))

/* 32-bit Rotate-right (used in SHA-256): */

#define ROTR32(b,x) (((x) >> (b)) | ((x) << (32 - (b))))

/* 64-bit Rotate-right (used in SHA-384 and SHA-512): */

#define ROTR64(b,x) (((x) >> (b)) | ((x) << (64 - (b))))

/* 32-bit Rotate-left (used in SHA-1): */

#define ROTL32(b,x) (((x) << (b)) | ((x) >> (32 - (b))))

/* Two of six logical functions used in SHA-1, SHA-256, SHA-384, and SHA-512: */

#define Ch(x,y,z) (((x) & (y)) ^ ((~(x)) & (z)))

#define Maj(x,y,z)  (((x) & (y)) ^ ((x) & (z)) ^ ((y) & (z)))

/* Function used in SHA-1: */

#define Parity(x,y,z) ((x) ^ (y) ^ (z))

/* Four of six logical functions used in SHA-256: */

#define Sigma0_256(x) (ROTR32(2,  (x)) ^ ROTR32(13, (x)) ^ ROTR32(22, (x)))

#define Sigma1_256(x) (ROTR32(6,  (x)) ^ ROTR32(11, (x)) ^ ROTR32(25, (x)))

#define sigma0_256(x) (ROTR32(7,  (x)) ^ ROTR32(18, (x)) ^ SHR(3 ,   (x)))

#define sigma1_256(x) (ROTR32(17, (x)) ^ ROTR32(19, (x)) ^ SHR(10,   (x)))

/* Four of six logical functions used in SHA-384 and SHA-512: */

#define Sigma0_512(x) (ROTR64(28, (x)) ^ ROTR64(34, (x)) ^ ROTR64(39, (x)))

#define Sigma1_512(x) (ROTR64(14, (x)) ^ ROTR64(18, (x)) ^ ROTR64(41, (x)))

#define sigma0_512(x) (ROTR64( 1, (x)) ^ ROTR64( 8, (x)) ^ SHR( 7,   (x)))

#define sigma1_512(x) (ROTR64(19, (x)) ^ ROTR64(61, (x)) ^ SHR( 6,   (x)))

/*** INTERNAL FUNCTION PROTOTYPES *************************************/

/* NOTE: These should not be accessed directly from outside this

 * library -- they are intended for private internal visibility/use

 * only.

 */

static void sha512_Last(SHA512_CTX*);

/*** SHA-XYZ INITIAL HASH VALUES AND CONSTANTS ************************/

/* Hash constant words K for SHA-1: */

#define K1_0_TO_19  0x5a827999UL

#define K1_20_TO_39 0x6ed9eba1UL

#define K1_40_TO_59 0x8f1bbcdcUL

#define K1_60_TO_79 0xca62c1d6UL

/* Initial hash value H for SHA-1: */

const sha2_word32 sha1_initial_hash_value[SHA1_DIGEST_LENGTH / sizeof(sha2_word32)] = {

  0x67452301UL,

  0xefcdab89UL,

  0x98badcfeUL,

  0x10325476UL,

  0xc3d2e1f0UL

};

/* Hash constant words K for SHA-256: */

static const sha2_word32 K256[64] = {

  0x428a2f98UL, 0x71374491UL, 0xb5c0fbcfUL, 0xe9b5dba5UL,

  0x3956c25bUL, 0x59f111f1UL, 0x923f82a4UL, 0xab1c5ed5UL,

  0xd807aa98UL, 0x12835b01UL, 0x243185beUL, 0x550c7dc3UL,

  0x72be5d74UL, 0x80deb1feUL, 0x9bdc06a7UL, 0xc19bf174UL,

  0xe49b69c1UL, 0xefbe4786UL, 0x0fc19dc6UL, 0x240ca1ccUL,

  0x2de92c6fUL, 0x4a7484aaUL, 0x5cb0a9dcUL, 0x76f988daUL,

  0x983e5152UL, 0xa831c66dUL, 0xb00327c8UL, 0xbf597fc7UL,

  0xc6e00bf3UL, 0xd5a79147UL, 0x06ca6351UL, 0x14292967UL,

  0x27b70a85UL, 0x2e1b2138UL, 0x4d2c6dfcUL, 0x53380d13UL,

  0x650a7354UL, 0x766a0abbUL, 0x81c2c92eUL, 0x92722c85UL,

  0xa2bfe8a1UL, 0xa81a664bUL, 0xc24b8b70UL, 0xc76c51a3UL,

  0xd192e819UL, 0xd6990624UL, 0xf40e3585UL, 0x106aa070UL,

  0x19a4c116UL, 0x1e376c08UL, 0x2748774cUL, 0x34b0bcb5UL,

  0x391c0cb3UL, 0x4ed8aa4aUL, 0x5b9cca4fUL, 0x682e6ff3UL,

  0x748f82eeUL, 0x78a5636fUL, 0x84c87814UL, 0x8cc70208UL,

  0x90befffaUL, 0xa4506cebUL, 0xbef9a3f7UL, 0xc67178f2UL

};

/* Initial hash value H for SHA-256: */

const sha2_word32 sha256_initial_hash_value[8] = {

  0x6a09e667UL,

  0xbb67ae85UL,

  0x3c6ef372UL,

  0xa54ff53aUL,

  0x510e527fUL,

  0x9b05688cUL,

  0x1f83d9abUL,

  0x5be0cd19UL

};

/* Hash constant words K for SHA-384 and SHA-512: */

static const sha2_word64 K512[80] = {

  0x428a2f98d728ae22ULL, 0x7137449123ef65cdULL,

  0xb5c0fbcfec4d3b2fULL, 0xe9b5dba58189dbbcULL,

  0x3956c25bf348b538ULL, 0x59f111f1b605d019ULL,

  0x923f82a4af194f9bULL, 0xab1c5ed5da6d8118ULL,

  0xd807aa98a3030242ULL, 0x12835b0145706fbeULL,

  0x243185be4ee4b28cULL, 0x550c7dc3d5ffb4e2ULL,

  0x72be5d74f27b896fULL, 0x80deb1fe3b1696b1ULL,

  0x9bdc06a725c71235ULL, 0xc19bf174cf692694ULL,

  0xe49b69c19ef14ad2ULL, 0xefbe4786384f25e3ULL,

  0x0fc19dc68b8cd5b5ULL, 0x240ca1cc77ac9c65ULL,

  0x2de92c6f592b0275ULL, 0x4a7484aa6ea6e483ULL,

  0x5cb0a9dcbd41fbd4ULL, 0x76f988da831153b5ULL,

  0x983e5152ee66dfabULL, 0xa831c66d2db43210ULL,

  0xb00327c898fb213fULL, 0xbf597fc7beef0ee4ULL,

  0xc6e00bf33da88fc2ULL, 0xd5a79147930aa725ULL,

  0x06ca6351e003826fULL, 0x142929670a0e6e70ULL,

  0x27b70a8546d22ffcULL, 0x2e1b21385c26c926ULL,

  0x4d2c6dfc5ac42aedULL, 0x53380d139d95b3dfULL,

  0x650a73548baf63deULL, 0x766a0abb3c77b2a8ULL,

  0x81c2c92e47edaee6ULL, 0x92722c851482353bULL,

  0xa2bfe8a14cf10364ULL, 0xa81a664bbc423001ULL,

  0xc24b8b70d0f89791ULL, 0xc76c51a30654be30ULL,

  0xd192e819d6ef5218ULL, 0xd69906245565a910ULL,

  0xf40e35855771202aULL, 0x106aa07032bbd1b8ULL,

  0x19a4c116b8d2d0c8ULL, 0x1e376c085141ab53ULL,

  0x2748774cdf8eeb99ULL, 0x34b0bcb5e19b48a8ULL,

  0x391c0cb3c5c95a63ULL, 0x4ed8aa4ae3418acbULL,

  0x5b9cca4f7763e373ULL, 0x682e6ff3d6b2b8a3ULL,

  0x748f82ee5defb2fcULL, 0x78a5636f43172f60ULL,

  0x84c87814a1f0ab72ULL, 0x8cc702081a6439ecULL,

  0x90befffa23631e28ULL, 0xa4506cebde82bde9ULL,

  0xbef9a3f7b2c67915ULL, 0xc67178f2e372532bULL,

  0xca273eceea26619cULL, 0xd186b8c721c0c207ULL,

  0xeada7dd6cde0eb1eULL, 0xf57d4f7fee6ed178ULL,

  0x06f067aa72176fbaULL, 0x0a637dc5a2c898a6ULL,

  0x113f9804bef90daeULL, 0x1b710b35131c471bULL,

  0x28db77f523047d84ULL, 0x32caab7b40c72493ULL,

  0x3c9ebe0a15c9bebcULL, 0x431d67c49c100d4cULL,

  0x4cc5d4becb3e42b6ULL, 0x597f299cfc657e2aULL,

  0x5fcb6fab3ad6faecULL, 0x6c44198c4a475817ULL

};

/* Initial hash value H for SHA-512 */

const sha2_word64 sha512_initial_hash_value[8] = {

  0x6a09e667f3bcc908ULL,

  0xbb67ae8584caa73bULL,

  0x3c6ef372fe94f82bULL,

  0xa54ff53a5f1d36f1ULL,

  0x510e527fade682d1ULL,

  0x9b05688c2b3e6c1fULL,

  0x1f83d9abfb41bd6bULL,

  0x5be0cd19137e2179ULL

};

/* Initial hash value H for SHA-384 */

const sha2_word64 sha384_initial_hash_value[8] = {

  0xcbbb9d5dc1059ed8ULL,

  0x629a292a367cd507ULL,

  0x9159015a3070dd17ULL,

  0x152fecd8f70e5939ULL,

  0x67332667ffc00b31ULL,

  0x8eb44a8768581511ULL,

  0xdb0c2e0d64f98fa7ULL,

  0x47b5481dbefa4fa4ULL

};

/*

 * Constant used by SHA256/384/512_End() functions for converting the

 * digest to a readable hexadecimal character string:

 */

static const char *sha2_hex_digits = "0123456789abcdef";

/*** SHA-1: ***********************************************************/

void sha1_Init(SHA1_CTX* context) {

  MEMCPY_BCOPY(context->state, sha1_initial_hash_value, SHA1_DIGEST_LENGTH);

  memzero(context->buffer, SHA1_BLOCK_LENGTH);

  context->bitcount = 0;

}

#ifdef SHA2_UNROLL_TRANSFORM

/* Unrolled SHA-1 round macros: */

#define ROUND1_0_TO_15(a,b,c,d,e)       \

  (e) = ROTL32(5, (a)) + Ch((b), (c), (d)) + (e) +  \

       K1_0_TO_19 + ( W1[j] = *data++ );    \

  (b) = ROTL32(30, (b));  \

  j++;

#define ROUND1_16_TO_19(a,b,c,d,e)  \

  T1 = W1[(j+13)&0x0f] ^ W1[(j+8)&0x0f] ^ W1[(j+2)&0x0f] ^ W1[j&0x0f];  \

  (e) = ROTL32(5, a) + Ch(b,c,d) + e + K1_0_TO_19 + ( W1[j&0x0f] = ROTL32(1, T1) ); \

  (b) = ROTL32(30, b);  \

  j++;

#define ROUND1_20_TO_39(a,b,c,d,e)  \

  T1 = W1[(j+13)&0x0f] ^ W1[(j+8)&0x0f] ^ W1[(j+2)&0x0f] ^ W1[j&0x0f];  \

  (e) = ROTL32(5, a) + Parity(b,c,d) + e + K1_20_TO_39 + ( W1[j&0x0f] = ROTL32(1, T1) );  \

  (b) = ROTL32(30, b);  \

  j++;

#define ROUND1_40_TO_59(a,b,c,d,e)  \

  T1 = W1[(j+13)&0x0f] ^ W1[(j+8)&0x0f] ^ W1[(j+2)&0x0f] ^ W1[j&0x0f];  \

  (e) = ROTL32(5, a) + Maj(b,c,d) + e + K1_40_TO_59 + ( W1[j&0x0f] = ROTL32(1, T1) ); \

  (b) = ROTL32(30, b);  \

  j++;

#define ROUND1_60_TO_79(a,b,c,d,e)  \

  T1 = W1[(j+13)&0x0f] ^ W1[(j+8)&0x0f] ^ W1[(j+2)&0x0f] ^ W1[j&0x0f];  \

  (e) = ROTL32(5, a) + Parity(b,c,d) + e + K1_60_TO_79 + ( W1[j&0x0f] = ROTL32(1, T1) );  \

  (b) = ROTL32(30, b);  \

  j++;

void sha1_Transform(const sha2_word32* state_in, const sha2_word32* data, sha2_word32* state_out) {

  sha2_word32 a = 0, b = 0, c = 0, d = 0, e = 0;

  sha2_word32 T1 = 0;

  sha2_word32 W1[16] = {0};

  int   j = 0;

  /* Initialize registers with the prev. intermediate value */

  a = state_in[0];

  b = state_in[1];

  c = state_in[2];

  d = state_in[3];

  e = state_in[4];

  j = 0;

  /* Rounds 0 to 15 unrolled: */

  ROUND1_0_TO_15(a,b,c,d,e);

  ROUND1_0_TO_15(e,a,b,c,d);

  ROUND1_0_TO_15(d,e,a,b,c);

  ROUND1_0_TO_15(c,d,e,a,b);

  ROUND1_0_TO_15(b,c,d,e,a);

  ROUND1_0_TO_15(a,b,c,d,e);

  ROUND1_0_TO_15(e,a,b,c,d);

  ROUND1_0_TO_15(d,e,a,b,c);

  ROUND1_0_TO_15(c,d,e,a,b);

  ROUND1_0_TO_15(b,c,d,e,a);

  ROUND1_0_TO_15(a,b,c,d,e);

  ROUND1_0_TO_15(e,a,b,c,d);

  ROUND1_0_TO_15(d,e,a,b,c);

  ROUND1_0_TO_15(c,d,e,a,b);

  ROUND1_0_TO_15(b,c,d,e,a);

  ROUND1_0_TO_15(a,b,c,d,e);

  /* Rounds 16 to 19 unrolled: */

  ROUND1_16_TO_19(e,a,b,c,d);

  ROUND1_16_TO_19(d,e,a,b,c);

  ROUND1_16_TO_19(c,d,e,a,b);

  ROUND1_16_TO_19(b,c,d,e,a);

  /* Rounds 20 to 39 unrolled: */

  ROUND1_20_TO_39(a,b,c,d,e);

  ROUND1_20_TO_39(e,a,b,c,d);

  ROUND1_20_TO_39(d,e,a,b,c);

  ROUND1_20_TO_39(c,d,e,a,b);

  ROUND1_20_TO_39(b,c,d,e,a);

  ROUND1_20_TO_39(a,b,c,d,e);

  ROUND1_20_TO_39(e,a,b,c,d);

  ROUND1_20_TO_39(d,e,a,b,c);

  ROUND1_20_TO_39(c,d,e,a,b);

  ROUND1_20_TO_39(b,c,d,e,a);

  ROUND1_20_TO_39(a,b,c,d,e);

  ROUND1_20_TO_39(e,a,b,c,d);

  ROUND1_20_TO_39(d,e,a,b,c);

  ROUND1_20_TO_39(c,d,e,a,b);

  ROUND1_20_TO_39(b,c,d,e,a);

  ROUND1_20_TO_39(a,b,c,d,e);

  ROUND1_20_TO_39(e,a,b,c,d);

  ROUND1_20_TO_39(d,e,a,b,c);

  ROUND1_20_TO_39(c,d,e,a,b);

  ROUND1_20_TO_39(b,c,d,e,a);

  /* Rounds 40 to 59 unrolled: */

  ROUND1_40_TO_59(a,b,c,d,e);

  ROUND1_40_TO_59(e,a,b,c,d);

  ROUND1_40_TO_59(d,e,a,b,c);

  ROUND1_40_TO_59(c,d,e,a,b);

  ROUND1_40_TO_59(b,c,d,e,a);

  ROUND1_40_TO_59(a,b,c,d,e);

  ROUND1_40_TO_59(e,a,b,c,d);

  ROUND1_40_TO_59(d,e,a,b,c);

  ROUND1_40_TO_59(c,d,e,a,b);

  ROUND1_40_TO_59(b,c,d,e,a);

  ROUND1_40_TO_59(a,b,c,d,e);

  ROUND1_40_TO_59(e,a,b,c,d);

  ROUND1_40_TO_59(d,e,a,b,c);

  ROUND1_40_TO_59(c,d,e,a,b);

  ROUND1_40_TO_59(b,c,d,e,a);

  ROUND1_40_TO_59(a,b,c,d,e);

  ROUND1_40_TO_59(e,a,b,c,d);

  ROUND1_40_TO_59(d,e,a,b,c);

  ROUND1_40_TO_59(c,d,e,a,b);

  ROUND1_40_TO_59(b,c,d,e,a);

  /* Rounds 60 to 79 unrolled: */

  ROUND1_60_TO_79(a,b,c,d,e);

  ROUND1_60_TO_79(e,a,b,c,d);

  ROUND1_60_TO_79(d,e,a,b,c);

  ROUND1_60_TO_79(c,d,e,a,b);

  ROUND1_60_TO_79(b,c,d,e,a);

  ROUND1_60_TO_79(a,b,c,d,e);

  ROUND1_60_TO_79(e,a,b,c,d);

  ROUND1_60_TO_79(d,e,a,b,c);

  ROUND1_60_TO_79(c,d,e,a,b);

  ROUND1_60_TO_79(b,c,d,e,a);

  ROUND1_60_TO_79(a,b,c,d,e);

  ROUND1_60_TO_79(e,a,b,c,d);

  ROUND1_60_TO_79(d,e,a,b,c);

  ROUND1_60_TO_79(c,d,e,a,b);

  ROUND1_60_TO_79(b,c,d,e,a);

  ROUND1_60_TO_79(a,b,c,d,e);

  ROUND1_60_TO_79(e,a,b,c,d);

  ROUND1_60_TO_79(d,e,a,b,c);

  ROUND1_60_TO_79(c,d,e,a,b);

  ROUND1_60_TO_79(b,c,d,e,a);

  /* Compute the current intermediate hash value */

  state_out[0] = state_in[0] + a;

  state_out[1] = state_in[1] + b;

  state_out[2] = state_in[2] + c;

  state_out[3] = state_in[3] + d;

  state_out[4] = state_in[4] + e;

  /* Clean up */

  a = b = c = d = e = T1 = 0;

}

#else  /* SHA2_UNROLL_TRANSFORM */

void sha1_Transform(const sha2_word32* state_in, const sha2_word32* data, sha2_word32* state_out) {

  sha2_word32 a = 0, b = 0, c = 0, d = 0, e = 0;

  sha2_word32 T1 = 0;

  sha2_word32 W1[16] = {0};

  int   j = 0;

  /* Initialize registers with the prev. intermediate value */

  a = state_in[0];

  b = state_in[1];

  c = state_in[2];

  d = state_in[3];

  e = state_in[4];

  j = 0;

  do {

    T1 = ROTL32(5, a) + Ch(b, c, d) + e + K1_0_TO_19 + (W1[j] = *data++);

    e = d;

    d = c;

    c = ROTL32(30, b);

    b = a;

    a = T1;

    j++;

  } while (j < 16);

  do {

    T1 = W1[(j+13)&0x0f] ^ W1[(j+8)&0x0f] ^ W1[(j+2)&0x0f] ^ W1[j&0x0f];

    T1 = ROTL32(5, a) + Ch(b,c,d) + e + K1_0_TO_19 + (W1[j&0x0f] = ROTL32(1, T1));

    e = d;

    d = c;

    c = ROTL32(30, b);

    b = a;

    a = T1;

    j++;

  } while (j < 20);

  do {

    T1 = W1[(j+13)&0x0f] ^ W1[(j+8)&0x0f] ^ W1[(j+2)&0x0f] ^ W1[j&0x0f];

    T1 = ROTL32(5, a) + Parity(b,c,d) + e + K1_20_TO_39 + (W1[j&0x0f] = ROTL32(1, T1));

    e = d;

    d = c;

    c = ROTL32(30, b);

    b = a;

    a = T1;

    j++;

  } while (j < 40);

  do {

    T1 = W1[(j+13)&0x0f] ^ W1[(j+8)&0x0f] ^ W1[(j+2)&0x0f] ^ W1[j&0x0f];

    T1 = ROTL32(5, a) + Maj(b,c,d) + e + K1_40_TO_59 + (W1[j&0x0f] = ROTL32(1, T1));

    e = d;

    d = c;

    c = ROTL32(30, b);

    b = a;

    a = T1;

    j++;

  } while (j < 60);

  do {

    T1 = W1[(j+13)&0x0f] ^ W1[(j+8)&0x0f] ^ W1[(j+2)&0x0f] ^ W1[j&0x0f];

    T1 = ROTL32(5, a) + Parity(b,c,d) + e + K1_60_TO_79 + (W1[j&0x0f] = ROTL32(1, T1));

    e = d;

    d = c;

    c = ROTL32(30, b);

    b = a;

    a = T1;

    j++;

  } while (j < 80);

  /* Compute the current intermediate hash value */

  state_out[0] = state_in[0] + a;

  state_out[1] = state_in[1] + b;

  state_out[2] = state_in[2] + c;

  state_out[3] = state_in[3] + d;

  state_out[4] = state_in[4] + e;

  /* Clean up */

  a = b = c = d = e = T1 = 0;

}

#endif /* SHA2_UNROLL_TRANSFORM */

void sha1_Update(SHA1_CTX* context, const sha2_byte *data, size_t len) {

  unsigned int  freespace = 0, usedspace = 0;

  if (len == 0) {

    /* Calling with no data is valid - we do nothing */

    return;

  }

  usedspace = (context->bitcount >> 3) % SHA1_BLOCK_LENGTH;

  if (usedspace > 0) {

    /* Calculate how much free space is available in the buffer */

    freespace = SHA1_BLOCK_LENGTH - usedspace;

    if (len >= freespace) {

      /* Fill the buffer completely and process it */

      MEMCPY_BCOPY(((uint8_t*)context->buffer) + usedspace, data, freespace);

      context->bitcount += freespace << 3;

      len -= freespace;

      data += freespace;

#if BYTE_ORDER == LITTLE_ENDIAN

      /* Convert TO host byte order */

      for (int j = 0; j < 16; j++) {

        REVERSE32(context->buffer[j],context->buffer[j]);

      }

#endif

      sha1_Transform(context->state, context->buffer, context->state);

    } else {

      /* The buffer is not yet full */

      MEMCPY_BCOPY(((uint8_t*)context->buffer) + usedspace, data, len);

      context->bitcount += len << 3;

      /* Clean up: */

      usedspace = freespace = 0;

      return;

    }

  }

  while (len >= SHA1_BLOCK_LENGTH) {

    /* Process as many complete blocks as we can */

    MEMCPY_BCOPY(context->buffer, data, SHA1_BLOCK_LENGTH);

#if BYTE_ORDER == LITTLE_ENDIAN

    /* Convert TO host byte order */

    for (int j = 0; j < 16; j++) {

      REVERSE32(context->buffer[j],context->buffer[j]);

    }

#endif

    sha1_Transform(context->state, context->buffer, context->state);

    context->bitcount += SHA1_BLOCK_LENGTH << 3;

    len -= SHA1_BLOCK_LENGTH;

    data += SHA1_BLOCK_LENGTH;

  }

  if (len > 0) {

    /* There's left-overs, so save 'em */

    MEMCPY_BCOPY(context->buffer, data, len);

    context->bitcount += len << 3;

  }

  /* Clean up: */

  usedspace = freespace = 0;

}

void sha1_Final(SHA1_CTX* context, sha2_byte digest[SHA1_DIGEST_LENGTH]) {

  unsigned int  usedspace = 0;

  /* If no digest buffer is passed, we don't bother doing this: */

  if (digest != (sha2_byte*)0) {

    usedspace = (context->bitcount >> 3) % SHA1_BLOCK_LENGTH;

    /* Begin padding with a 1 bit: */

    ((uint8_t*)context->buffer)[usedspace++] = 0x80;

    if (usedspace > SHA1_SHORT_BLOCK_LENGTH) {

      memzero(((uint8_t*)context->buffer) + usedspace, SHA1_BLOCK_LENGTH - usedspace);

#if BYTE_ORDER == LITTLE_ENDIAN

      /* Convert TO host byte order */

      for (int j = 0; j < 16; j++) {

        REVERSE32(context->buffer[j],context->buffer[j]);

      }

#endif

      /* Do second-to-last transform: */

      sha1_Transform(context->state, context->buffer, context->state);

      /* And prepare the last transform: */

      usedspace = 0;

    }

    /* Set-up for the last transform: */

    memzero(((uint8_t*)context->buffer) + usedspace, SHA1_SHORT_BLOCK_LENGTH - usedspace);

#if BYTE_ORDER == LITTLE_ENDIAN

    /* Convert TO host byte order */

    for (int j = 0; j < 14; j++) {

      REVERSE32(context->buffer[j],context->buffer[j]);

    }

#endif

    /* Set the bit count: */

    context->buffer[14] = context->bitcount >> 32;

    context->buffer[15] = context->bitcount & 0xffffffff;

    /* Final transform: */

    sha1_Transform(context->state, context->buffer, context->state);

#if BYTE_ORDER == LITTLE_ENDIAN

    /* Convert FROM host byte order */

    for (int j = 0; j < 5; j++) {

      REVERSE32(context->state[j],context->state[j]);

    }

#endif

    MEMCPY_BCOPY(digest, context->state, SHA1_DIGEST_LENGTH);

  }

  /* Clean up state data: */

  memzero(context, sizeof(SHA1_CTX));

  usedspace = 0;

}

char *sha1_End(SHA1_CTX* context, char buffer[SHA1_DIGEST_STRING_LENGTH]) {

  sha2_byte digest[SHA1_DIGEST_LENGTH] = {0}, *d = digest;

  int   i = 0;

  if (buffer != (char*)0) {

    sha1_Final(context, digest);

    for (i = 0; i < SHA1_DIGEST_LENGTH; i++) {

      *buffer++ = sha2_hex_digits[(*d & 0xf0) >> 4];

      *buffer++ = sha2_hex_digits[*d & 0x0f];

      d++;

    }

    *buffer = (char)0;

  } else {

    memzero(context, sizeof(SHA1_CTX));

  }

  memzero(digest, SHA1_DIGEST_LENGTH);

  return buffer;

}

void sha1_Raw(const sha2_byte* data, size_t len, uint8_t digest[SHA1_DIGEST_LENGTH]) {

  SHA1_CTX  context = {0};

  sha1_Init(&context);

  sha1_Update(&context, data, len);

  sha1_Final(&context, digest);

}

char* sha1_Data(const sha2_byte* data, size_t len, char digest[SHA1_DIGEST_STRING_LENGTH]) {

  SHA1_CTX  context = {0};

  sha1_Init(&context);

  sha1_Update(&context, data, len);

  return sha1_End(&context, digest);

}

/*** SHA-256: *********************************************************/

void sha256_Init(SHA256_CTX* context) {

  if (context == (SHA256_CTX*)0) {

    return;

  }

  MEMCPY_BCOPY(context->state, sha256_initial_hash_value, SHA256_DIGEST_LENGTH);

  memzero(context->buffer, SHA256_BLOCK_LENGTH);

  context->bitcount = 0;

}

void sha256_Init_ex(SHA256_CTX *context, const uint32_t state[8], uint64_t bitcount) {

  if (context == (SHA256_CTX*)0) {

    return;

  }

  MEMCPY_BCOPY(context->state, state, SHA256_DIGEST_LENGTH);

  memzero(context->buffer, SHA256_BLOCK_LENGTH);

  context->bitcount = bitcount;

}

#ifdef SHA2_UNROLL_TRANSFORM

/* Unrolled SHA-256 round macros: */

#define ROUND256_0_TO_15(a,b,c,d,e,f,g,h) \

  T1 = (h) + Sigma1_256(e) + Ch((e), (f), (g)) + \

       K256[j] + (W256[j] = *data++); \

  (d) += T1; \

  (h) = T1 + Sigma0_256(a) + Maj((a), (b), (c)); \

  j++

#define ROUND256(a,b,c,d,e,f,g,h) \

  s0 = W256[(j+1)&0x0f]; \

  s0 = sigma0_256(s0); \

  s1 = W256[(j+14)&0x0f]; \

  s1 = sigma1_256(s1); \

  T1 = (h) + Sigma1_256(e) + Ch((e), (f), (g)) + K256[j] + \

       (W256[j&0x0f] += s1 + W256[(j+9)&0x0f] + s0); \

  (d) += T1; \

  (h) = T1 + Sigma0_256(a) + Maj((a), (b), (c)); \

  j++

void sha256_Transform(const sha2_word32* state_in, const sha2_word32* data, sha2_word32* state_out) {

  sha2_word32 a = 0, b = 0, c = 0, d = 0, e = 0, f = 0, g = 0, h = 0, s0 = 0, s1 = 0;

  sha2_word32 T1 = 0;

  sha2_word32 W256[16] = {0};

  int   j = 0;

  /* Initialize registers with the prev. intermediate value */

  a = state_in[0];

  b = state_in[1];

  c = state_in[2];

  d = state_in[3];

  e = state_in[4];

  f = state_in[5];

  g = state_in[6];

  h = state_in[7];

  j = 0;

  do {

    /* Rounds 0 to 15 (unrolled): */

    ROUND256_0_TO_15(a,b,c,d,e,f,g,h);

    ROUND256_0_TO_15(h,a,b,c,d,e,f,g);

    ROUND256_0_TO_15(g,h,a,b,c,d,e,f);

    ROUND256_0_TO_15(f,g,h,a,b,c,d,e);

    ROUND256_0_TO_15(e,f,g,h,a,b,c,d);

    ROUND256_0_TO_15(d,e,f,g,h,a,b,c);

    ROUND256_0_TO_15(c,d,e,f,g,h,a,b);

    ROUND256_0_TO_15(b,c,d,e,f,g,h,a);

  } while (j < 16);

  /* Now for the remaining rounds to 64: */

  do {

    ROUND256(a,b,c,d,e,f,g,h);

    ROUND256(h,a,b,c,d,e,f,g);

    ROUND256(g,h,a,b,c,d,e,f);

    ROUND256(f,g,h,a,b,c,d,e);

    ROUND256(e,f,g,h,a,b,c,d);

    ROUND256(d,e,f,g,h,a,b,c);

    ROUND256(c,d,e,f,g,h,a,b);

    ROUND256(b,c,d,e,f,g,h,a);

  } while (j < 64);

  /* Compute the current intermediate hash value */

  state_out[0] = state_in[0] + a;

  state_out[1] = state_in[1] + b;

  state_out[2] = state_in[2] + c;

  state_out[3] = state_in[3] + d;

  state_out[4] = state_in[4] + e;

  state_out[5] = state_in[5] + f;

  state_out[6] = state_in[6] + g;

  state_out[7] = state_in[7] + h;

  /* Clean up */

  a = b = c = d = e = f = g = h = T1 = 0;

}

#else /* SHA2_UNROLL_TRANSFORM */

void sha256_Transform(const sha2_word32* state_in, const sha2_word32* data, sha2_word32* state_out) {

  sha2_word32 a = 0, b = 0, c = 0, d = 0, e = 0, f = 0, g = 0, h = 0, s0 = 0, s1 = 0;

  sha2_word32 T1 = 0, T2 = 0 , W256[16] = {0};

  int   j = 0;

  /* Initialize registers with the prev. intermediate value */

  a = state_in[0];

  b = state_in[1];

  c = state_in[2];

  d = state_in[3];

  e = state_in[4];

  f = state_in[5];

  g = state_in[6];

  h = state_in[7];

  j = 0;

  do {

    /* Apply the SHA-256 compression function to update a..h with copy */

    T1 = h + Sigma1_256(e) + Ch(e, f, g) + K256[j] + (W256[j] = *data++);

    T2 = Sigma0_256(a) + Maj(a, b, c);

    h = g;

    g = f;

    f = e;

    e = d + T1;

    d = c;

    c = b;

    b = a;

    a = T1 + T2;

    j++;

  } while (j < 16);

  do {

    /* Part of the message block expansion: */

    s0 = W256[(j+1)&0x0f];

    s0 = sigma0_256(s0);

    s1 = W256[(j+14)&0x0f];

    s1 = sigma1_256(s1);

    /* Apply the SHA-256 compression function to update a..h */

    T1 = h + Sigma1_256(e) + Ch(e, f, g) + K256[j] +

         (W256[j&0x0f] += s1 + W256[(j+9)&0x0f] + s0);

    T2 = Sigma0_256(a) + Maj(a, b, c);

    h = g;

    g = f;

    f = e;

    e = d + T1;

    d = c;

    c = b;

    b = a;

    a = T1 + T2;

    j++;

  } while (j < 64);

  /* Compute the current intermediate hash value */

  state_out[0] = state_in[0] + a;

  state_out[1] = state_in[1] + b;

  state_out[2] = state_in[2] + c;

  state_out[3] = state_in[3] + d;

  state_out[4] = state_in[4] + e;

  state_out[5] = state_in[5] + f;

  state_out[6] = state_in[6] + g;

  state_out[7] = state_in[7] + h;

  /* Clean up */

  a = b = c = d = e = f = g = h = T1 = T2 = 0;

}

#endif /* SHA2_UNROLL_TRANSFORM */

void sha256_Update(SHA256_CTX* context, const sha2_byte *data, size_t len) {

  unsigned int  freespace = 0, usedspace = 0;

  if (len == 0) {

    /* Calling with no data is valid - we do nothing */

    return;

  }

  usedspace = (context->bitcount >> 3) % SHA256_BLOCK_LENGTH;

  if (usedspace > 0) {

    /* Calculate how much free space is available in the buffer */

    freespace = SHA256_BLOCK_LENGTH - usedspace;

    if (len >= freespace) {

      /* Fill the buffer completely and process it */

      MEMCPY_BCOPY(((uint8_t*)context->buffer) + usedspace, data, freespace);

      context->bitcount += freespace << 3;

      len -= freespace;

      data += freespace;

#if BYTE_ORDER == LITTLE_ENDIAN

      /* Convert TO host byte order */

      for (int j = 0; j < 16; j++) {

        REVERSE32(context->buffer[j],context->buffer[j]);

      }

#endif

      sha256_Transform(context->state, context->buffer, context->state);

    } else {

      /* The buffer is not yet full */

      MEMCPY_BCOPY(((uint8_t*)context->buffer) + usedspace, data, len);

      context->bitcount += len << 3;

      /* Clean up: */

      usedspace = freespace = 0;

      return;

    }

  }

  while (len >= SHA256_BLOCK_LENGTH) {

    /* Process as many complete blocks as we can */

    MEMCPY_BCOPY(context->buffer, data, SHA256_BLOCK_LENGTH);

#if BYTE_ORDER == LITTLE_ENDIAN

    /* Convert TO host byte order */

    for (int j = 0; j < 16; j++) {

      REVERSE32(context->buffer[j],context->buffer[j]);

    }

#endif

    sha256_Transform(context->state, context->buffer, context->state);

    context->bitcount += SHA256_BLOCK_LENGTH << 3;

    len -= SHA256_BLOCK_LENGTH;

    data += SHA256_BLOCK_LENGTH;

  }

  if (len > 0) {

    /* There's left-overs, so save 'em */

    MEMCPY_BCOPY(context->buffer, data, len);

    context->bitcount += len << 3;

  }

  /* Clean up: */

  usedspace = freespace = 0;

}

void sha256_Final(SHA256_CTX* context, sha2_byte digest[SHA256_DIGEST_LENGTH]) {

  unsigned int  usedspace = 0;

  /* If no digest buffer is passed, we don't bother doing this: */

  if (digest != (sha2_byte*)0) {

    usedspace = (context->bitcount >> 3) % SHA256_BLOCK_LENGTH;

    /* Begin padding with a 1 bit: */

    ((uint8_t*)context->buffer)[usedspace++] = 0x80;

    if (usedspace > SHA256_SHORT_BLOCK_LENGTH) {

      memzero(((uint8_t*)context->buffer) + usedspace, SHA256_BLOCK_LENGTH - usedspace);

#if BYTE_ORDER == LITTLE_ENDIAN

      /* Convert TO host byte order */

      for (int j = 0; j < 16; j++) {

        REVERSE32(context->buffer[j],context->buffer[j]);

      }

#endif

      /* Do second-to-last transform: */

      sha256_Transform(context->state, context->buffer, context->state);

      /* And prepare the last transform: */

      usedspace = 0;

    }

    /* Set-up for the last transform: */

    memzero(((uint8_t*)context->buffer) + usedspace, SHA256_SHORT_BLOCK_LENGTH - usedspace);

#if BYTE_ORDER == LITTLE_ENDIAN

    /* Convert TO host byte order */

    for (int j = 0; j < 14; j++) {

      REVERSE32(context->buffer[j],context->buffer[j]);

    }

#endif

    /* Set the bit count: */

    context->buffer[14] = context->bitcount >> 32;

    context->buffer[15] = context->bitcount & 0xffffffff;

    /* Final transform: */

    sha256_Transform(context->state, context->buffer, context->state);

#if BYTE_ORDER == LITTLE_ENDIAN

    /* Convert FROM host byte order */

    for (int j = 0; j < 8; j++) {

      REVERSE32(context->state[j],context->state[j]);

    }

#endif

    MEMCPY_BCOPY(digest, context->state, SHA256_DIGEST_LENGTH);

  }

  /* Clean up state data: */

  memzero(context, sizeof(SHA256_CTX));

  usedspace = 0;

}

char *sha256_End(SHA256_CTX* context, char buffer[SHA256_DIGEST_STRING_LENGTH]) {

  sha2_byte digest[SHA256_DIGEST_LENGTH] = {0}, *d = digest;

  int   i = 0;

  if (buffer != (char*)0) {

    sha256_Final(context, digest);

    for (i = 0; i < SHA256_DIGEST_LENGTH; i++) {

      *buffer++ = sha2_hex_digits[(*d & 0xf0) >> 4];

      *buffer++ = sha2_hex_digits[*d & 0x0f];

      d++;

    }

    *buffer = (char)0;

  } else {

    memzero(context, sizeof(SHA256_CTX));

  }

  memzero(digest, SHA256_DIGEST_LENGTH);

  return buffer;

}

void sha256_Raw(const sha2_byte* data, size_t len, uint8_t digest[SHA256_DIGEST_LENGTH]) {

  SHA256_CTX  context = {0};

  sha256_Init(&context);

  sha256_Update(&context, data, len);

  sha256_Final(&context, digest);

}

char* sha256_Data(const sha2_byte* data, size_t len, char digest[SHA256_DIGEST_STRING_LENGTH]) {

  SHA256_CTX  context = {0};

  sha256_Init(&context);

  sha256_Update(&context, data, len);

  return sha256_End(&context, digest);

}

/*** SHA-512 and SHA-384: *********************************************/

void sha512_Init(SHA512_CTX* context) {

  if (context == (SHA512_CTX*)0) {

    return;

  }

  MEMCPY_BCOPY(context->state, sha512_initial_hash_value, SHA512_DIGEST_LENGTH);

  memzero(context->buffer, SHA512_BLOCK_LENGTH);

  context->bitcount[0] = context->bitcount[1] =  0;

}

static void sha384_Init(SHA512_CTX* context) {

  if (context == (SHA512_CTX*)0) {

    return;

  }

  MEMCPY_BCOPY(context->state, sha384_initial_hash_value, SHA512_DIGEST_LENGTH);

  memzero(context->buffer, SHA512_BLOCK_LENGTH);

  context->bitcount[0] = context->bitcount[1] =  0;

}

#ifdef SHA2_UNROLL_TRANSFORM

/* Unrolled SHA-512 round macros: */

#define ROUND512_0_TO_15(a,b,c,d,e,f,g,h) \

  T1 = (h) + Sigma1_512(e) + Ch((e), (f), (g)) + \

             K512[j] + (W512[j] = *data++); \

  (d) += T1; \

  (h) = T1 + Sigma0_512(a) + Maj((a), (b), (c)); \

  j++

#define ROUND512(a,b,c,d,e,f,g,h) \

  s0 = W512[(j+1)&0x0f]; \

  s0 = sigma0_512(s0); \

  s1 = W512[(j+14)&0x0f]; \

  s1 = sigma1_512(s1); \

  T1 = (h) + Sigma1_512(e) + Ch((e), (f), (g)) + K512[j] + \

             (W512[j&0x0f] += s1 + W512[(j+9)&0x0f] + s0); \

  (d) += T1; \

  (h) = T1 + Sigma0_512(a) + Maj((a), (b), (c)); \

  j++

void sha512_Transform(const sha2_word64* state_in, const sha2_word64* data, sha2_word64* state_out) {

  sha2_word64 a = 0, b = 0, c = 0, d = 0, e = 0, f = 0, g = 0, h = 0, s0 = 0, s1 = 0;

  sha2_word64 T1 = 0, W512[16] = {0};

  int   j = 0;

  /* Initialize registers with the prev. intermediate value */

  a = state_in[0];

  b = state_in[1];

  c = state_in[2];

  d = state_in[3];

  e = state_in[4];

  f = state_in[5];

  g = state_in[6];

  h = state_in[7];

  j = 0;

  do {

    ROUND512_0_TO_15(a,b,c,d,e,f,g,h);

    ROUND512_0_TO_15(h,a,b,c,d,e,f,g);

    ROUND512_0_TO_15(g,h,a,b,c,d,e,f);

    ROUND512_0_TO_15(f,g,h,a,b,c,d,e);

    ROUND512_0_TO_15(e,f,g,h,a,b,c,d);

    ROUND512_0_TO_15(d,e,f,g,h,a,b,c);

    ROUND512_0_TO_15(c,d,e,f,g,h,a,b);

    ROUND512_0_TO_15(b,c,d,e,f,g,h,a);

  } while (j < 16);